automate-session

automate-session is a skill for Claude Code, Codex from tomzx/agents. It costs 57 tokens per session (1,307 once invoked), scanned A, original, MIT.

A review of the current coding session to identify steps that could be handled automatically. It labels work as fully automatic, requiring a human review gate, or needing human judgment.

In plain words
What is it for?
Use it after completing a task to reconstruct the workflow, assess each step's automation potential, and suggest agents, scheduled jobs, or triggers.
Why use it?
It shows where repeated manual work can be removed or reduced without hiding decisions that still need a person.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/tomzx/agents/automate-session
Any agent
npx skills add tomzx/agents --skill automate-session
Clone the repo
git clone --depth 1 https://github.com/tomzx/agents

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for automate-session

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomzx/agents/automate-session.svg)](https://agentmods.dev/skills/tomzx/agents/automate-session)
Your own site
<a href="https://agentmods.dev/skills/tomzx/agents/automate-session"><img src="https://agentmods.dev/badge/skills/tomzx/agents/automate-session.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,307 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.01307
Opus 5 $0.00028 $0.00654
Sonnet 5 $0.00011 $0.00261
Haiku 4.5 $0.00006 $0.00131

Measured 5d ago against content hash 4ba771df8fec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

automate-session scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/automate-session/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Automation Opportunities

Reflects on the current session and identifies which steps could have been handled autonomously, a scheduled agent, or a triggered hook, removing the user from the loop entirely or reducing their involvement to review-only.

Prerequisites

  • A session with at least some completed work (conversation history, git changes, or both)

Steps

1. Reconstruct the session workflow

Build a chronological list of the steps taken during this session. Sources to draw from:

  • Conversation turns: what did the user ask, decide, or approve?
  • git log --oneline since session start: what changed?
  • File reads, writes, edits made during the session
  • Any external tool calls (GitHub, Slack, etc.)

Produce a numbered step-by-step trace of the session as if writing a runbook someone else would follow.

2. Classify each step by automation potential

For each step in the trace, assign one of three labels:

Label Meaning
Auto Could run fully autonomously with no human input — deterministic, low-risk, well-scoped
Review-gate An agent could execute it, but a human checkpoint (approve / reject) makes sense before or after
Human Requires human judgment, creative direction, or irreversible external action with unclear scope

A step qualifies as Auto if:

  • Its inputs are available programmatically (git state, file content, API response)
  • Its output is verifiable (tests pass, lint clean, diff is small and scoped)
  • Failure is detectable and recoverable without human intervention
  • It follows a pattern used repeatedly in prior sessions

A step is Review-gate if it is automatable but touches shared state (pushes to a remote, sends a message, opens a PR) or produces output a human should sanity-check before it propagates.

A step is Human if it involves priority trade-offs, novel design decisions, or communication requiring context only the user holds.

3. Identify the automation patterns

Group the Auto and Review-gate steps into one or more named automation patterns. For each pattern, describe:

Read the full file on GitHub · 139 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 139 lines · 57 tokens per session scan A 4ba771df8fec

Subscribe to this mod's changes

automate-session is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 1,307 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.